© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62450
    Prev
    Next
    INDEX
    Explanations

    dynamic interaction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĩ¾
    -0.09
    liness
    -0.09
    NAME
    -0.09
    è¡¿
    -0.09
    èĬ
    -0.09
    apsed
    -0.08
    åħ¬åħ±æľįåĬ¡
    -0.08
    çĭIJ
    -0.08
     trem
    -0.08
    öh
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.11
    _reporting
    0.09
    æīĢåľ¨
    0.09
    ä¸įåIJ«
    0.08
    éĺĶ
    0.08
    ALSE
    0.08
    istically
    0.08
    å·½
    0.08
    åıĺåĮĸ
    0.08
    strate
    0.08
    Activations Density 0.023%

    No Known Activations